Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cabbfa47ab8443f5cb53fe17df4baaef7d3055f028b00bbf6f357f47f947e6bf
+oid sha256:a9a2020e1e81d0db67dfcd552427f0a1a14ec3f0d786a74ed0dad73ca0464dfe
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc08e0ef8598d3f8e0bb6bb3ab6f1422af5d541337571be232fb65db89a720e0
+oid sha256:397e8a23b7552f60370d1700a97b449a0325dda9181fdf7c74ea250d27578e23
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4059d4b32af53dd16d1f00e9de12604f594b8995706d01b51e939355730bad
+oid sha256:30bafe9aa09d6f08852f65e3dd3a748ba867975cde5b463006fc3b71b5ae9261
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7f6bd9c5d892976d390d30aa3c5c56cd57489666bed2f4e417fb5cd59a9f43
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1,
+  "epoch": 2.4,
   "eval_steps": 3,
-  "global_step": 21,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,21 @@
       "eval_samples_per_second": 13.979,
       "eval_steps_per_second": 2.467,
       "step": 21
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.9233430624008179,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6105,
+      "step": 24
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.1175633668899536,
+      "eval_runtime": 1.2153,
+      "eval_samples_per_second": 13.988,
+      "eval_steps_per_second": 2.468,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -139,7 +154,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.941532217802752e+16,
+  "total_flos": 3.368098823405568e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null